RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Training Loop Update For Gen vs. Disc

Open

#1,079 opened on Aug 23, 2023

View on GitHub
 (2 comments) (0 reactions) (0 assignees)Python (2,849 forks)batch import
good first issue

Repository metrics

Stars
 (18,427 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Hello,

I've read i few articles that suggest it may make sense at certain stages/iterations of training to update the training loop where the Generator is updated at a ratio of 2:1 versus the Discriminator. I am a hobbyist at best, and was wondering if anyone could provide insight into where/how to implement this option in the code versus me trying to figure out over the next month :)

Contributor guide

Research direction
Locate the training loop in the codebase (likely in train.py or similar). Search for where Generator and Discriminator are updated sequentially. Implement a configuration parameter (e.g., 'gen disc ratio') that controls how often the Generator is updated relative to the Discriminator (e.g., 2:1 means Generator updates twice per Discriminator update). Modify the loop to skip Discriminator updates until the Generator has updated the specified number of times.
Tech stack
pythonpytorch
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50